© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34678
    Prev
    Next
    INDEX
    Explanations

    arithmetic expressions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric tokens (digits and numbers) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ふと
    -1.34
    ⎔
    -1.31
     procédures
    -1.26
    apparently
    -1.20
    generally
    -1.16
    ホント
    -1.13
    particularly
    -1.13
    
    -1.12
    frequently
    -1.12
     semblent
    -1.09
    POSITIVE LOGITS
     tries
    1.38
     first
    1.37
     gives
    1.20
     nine
    1.13
     three
    1.11
     undeniably
    1.10
     after
    1.09
     believes
    1.09
     one
    1.09
     makes
    1.09
    Activations Density 0.049%

    No Known Activations